Performance Analysis of GAN Approaches in the Portable Chest X-Ray Synthetic Image Generation for COVID-19 Screening

COVID-19 mainly affects lung tissues, aspect that makes chest X-ray imaging useful to visualize this damage. In the context of the global pandemic, portable devices are advantageous for the daily practice. Furthermore, Computer-aided Diagnosis systems developed with Deep Learning algorithms can support the clinicians while making decisions. However, data scarcity is an issue that hinders this process. Thus, in this work, we propose the performance analysis of 3 different state-of-the-art Generative Adversarial Networks (GAN) approaches that are used for synthetic image generation to improve the task of automatic COVID-19 screening using chest X-ray images provided by portable devices. Particularly, the results demonstrate a significant improvement in terms of accuracy, that raises 5.28% using the images generated by the best image translation model. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

A portable thermostatic molecular diagnosis device based on high-efficiency photothermal conversion material for rapid field detection of SARS-CoV-2.

The outbreak of the novel coronavirus (SARS-CoV-2) has seriously harmed human health and economic development worldwide. Studies have shown that timely diagnosis and isolation are the most effective ways to prevent the spread of the epidemic. However, the current polymerase chain reaction (PCR) based molecular diagnostic platform has the problems of expensive equipment, high operation difficulty, and the need for stable power resources support, so it is difficult to popularize in low-resource areas. This study established a portable (<300 g), low-cost (<$10), and reusable molecular diagnostic device based on solar energy photothermal conversion strategy, which creatively introduces a sunflower-like light tracking system to improve light utilization, making the device suitable for both high and low-light areas. The experimental results show that the device can detect SARS-CoV-2 nucleic acid samples as low as 1 aM within 30 min.

Development of a Novel Tabletop Device With Suction and Sanitization of Droplets against COVID-19.

Background Coronavirus disease 2019 and other viruses are transmissible by aerosols and droplets from infected persons. This study aimed to develop a portable device that can trap droplets and deactivate viruses, and verify whether the device in an enclosed room can suction droplets and sanitize them using a filter and an ultraviolet-C (UVC) light-emitting diode. Materials and methods The portable device was evaluated by placing it 50 cm away from the droplet initiation point. A particle image velocimetry laser dispersed into a sheet form was used to visualize the droplets splashed on the irradiated sagittal plane and captured using a charge-coupled device camera at 60 frames per second. The images were overlaid and calculated to determine the percentage of the droplets beyond the portable device. Droplets with a particle size larger than 50 µm that dispersed and were deposited more than 100 cm away were measured using a water-sensitive paper. The effect of UVC sanitization on viruses captured by a high-efficiency particulate air (HEPA) filter was determined using a plaque assay. Results The percentage of droplets was 13.4% and 1.1% with the portable device OFF and ON, respectively, indicating a 91.8% reduction. The deposited droplets were 86 pixels and 26 pixels with the portable device OFF and ON, respectively, indicating a 68.7% reduction. The UVC deactivated more than 99% of the viruses on the HEPA filter surface in 5 minutes. Conclusions Our novel portable device can suck and fall the dispersed droplets, and an active virus was not observed on the exhaust side.

Real Time Face Mask Detection Using Tiny YOLOv3

To stop the Covid-19 from spreading different techniques were developed and implemented. To make the use of face mask was effective to control the spread of it, as it transmits from one person to other. The use of face mask correctly is also important. The main objective is to develop a technique which can be used to monitor the people wearing face mask, not wearing the face mask or incorrect face mask and also to make use of the model which can be used on portable devices without the use of GPU for real time detection. The Yolov3-tiny model was used for detection. It achieved the mean average precision of 68% and it runs at 13 FPS without the use of GPU. The model was tested for image detection and also for real time detection. © 2022 IEEE.

Masked Face Recognition Using MobileNetV2

Masked face recognition has made great progress in the field of computer vision since the popularity of COVID-19 epidemic in 2020. In countries with severe outbreaks, people are required to wear masks in public. The current face recognition methods, which take use of the whole face as input data, are quite well established. However, while people are use of face masks, it will reduce the accuracy of face recognition. Therefore, we propose a mask wearing recognition method based on MobileNetV2 and solve the problem that many of models cannot be applied to portable devices or mobile terminals. The results indicate that this method has 98.30% accuracy in identifying the masked face. Simultaneously, a higher accuracy is obtained compared to VGG16. This approach has proven to be working well for the practical needs. © 2022 ACM.

GLAMP: Low-cost ozone and UV-C light-emitting portable device for disinfection of environments

With the Covid-19 pandemic outbreak, the demand for high-quality, low-cost, and safe use equipment for disinfecting hospitals, offices, schools, restaurants, supermarkets, etc., is growing. Although for years it has been known that the ozone produced by the UV-C technology irradiation is highly germicidal, its commercial use for enclosed spaces disinfection as a source of bacteria and viruses' infections is recent. Motivated by the above, this article introduces a low-cost ozone and UV-C light-emission portable device to satisfy the growing demand for disinfection of enclosed and unoccupied spaces. gLAMP, the proposal of this work, offers users a safe-to-use disinfection process by incorporating a pair of sensors into the design to measure air quality, keep users out of the risk area and streamline the ozone diffusion and ventilation processes in the area to be disinfected. As well as a mobile application to control and monitor the equipment and disinfection service remotely. Preliminary tests were carried out to verify the functionality of gLAMP and its potential commercial impact. © 2022 ACM.

CRISPR/Cas-engineered technology: Innovative approach for biosensor development.

On-site and real-time clinical monitoring have been progressed dramatically by integrating biosensor science with portable digital electronic technology. Clustered regularly interspaced short palindromic repeats (CRISPR) with association of RNA-guided nucleases (CrRNA-Cas enzymes) have achieved novel CRISPR/Cas biosensing science as a promising revolutionized diagnostic technology for portable and on-site healthcare monitoring and diagnostics. Among several available CRISPR/Cas systems, CRISPR/Cas12a and CRISPR/Cas13a conjugates are utilized broadly in biosensor design, because of their capability to cleave both target and non-target sequences. With the advantages of portability, cost-effectiveness, facile operation, high durability, and reproducibility, CRISPR/Cas-based biosensing techniques are a perfect choice for designing ultra-sensitive point-of-care diagnostic devices with amplified response signals. In the present review, we summarize the advances in the CRISPR/Cas-based biosensors with the focus on healthcare and diagnostic purposes. The cooperation of nanomaterial engineering with CRISPR/Cas biosensors is also represented to attain a promising viewpoint for offering novel user-friendly test kits for announcing ultra-low levels of diverse targets in the future.

Pulmonary-Restricted COVID-19 Informative Visual Screening Using Chest X-ray Images from Portable Devices

In the recent COVID-19 outbreak, chest X-rays were the main tool for diagnosing and monitoring the pathology. To prevent further spread of this disease, special circuits had to be implemented in the healthcare services. For this reason, these chest X-rays were captured with portable X-ray devices that compensate its lower quality and limitations with more deployment flexibility. However, most of the proposed computer-aided diagnosis methodologies were designed to work with traditional fixed X-ray machines and their performance is diminished when faced with these portable images. Additionally, given that the equipment needed to properly treat the disease (such as for life support and monitoring of vital signs) most of these systems learnt to identify these artifacts in the images instead of real clinically-significant variables. In this work, we present the first methodology forced to extract features exclusively from the pulmonary region of interest that is specially designed to work with these difficult portable images. Additionally, we generate a class activation map so the methodology also provides explainability to the results returned to the clinician. To ensure the robustness of our proposal, we tested the methodology with chest radiographs from patients diagnosed with COVID-19, pathologies similar to COVID-19 (such as other types of viral pneumonias) and healthy patients in different combinations with three convolutional networks from the state of the art (for a total of 9 studied scenarios). The experimentation confirms that our proposal is able to separate COVID-19 cases, reaching a 94.7% ± 1.34% of accuracy. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Comprehensive Analysis of the Screening of COVID-19 Approaches in Chest X-ray Images from Portable Devices

Computer-aided diagnosis plays an important role in the COVID-19 pandemic. Currently, it is recommended to use X-ray imaging to diagnose and assess the evolution in patients. Particularly, radiologists are asked to use portable acquisition devices to minimize the risk of cross-infection, facilitating an effective separation of suspected patients with other low-risk cases. In this work, we present an automatic COVID-19 screening, considering 6 representative state-of-the-art deep network architectures on a portable chest X-ray dataset that was specifically designed for this proposal. Exhaustive experimentation demonstrates that the models can separate COVID-19 cases from NON-COVID-19 cases, achieving a 97.68% of global accuracy. © 2021 ESANN Intelligence and Machine Learning. All rights reserved.

A safe and effective combination of UV and ozone

UVC radiation and ozone are known to be effective sanitizing agents. Therefore, they have been proposed in many applications during the pandemic outbreak since they are exempt from the storage, transportation and waste disposal drawbacks of chemical agents. However, both are effective on SARS-COV 2 at levels dangerous for humans. This work shows a portable device designed to treat the indoor environment with an ozone concentration where rise time, treatment value, and cleaning time are carefully controlled and traced not to harm people. When persons are present, the environmental air can be treated with UVC in an enclosed duct without exposure to harmful radiation. The UV source geometry and the duct's inner surface are designed to maximize the radiation dose delivered to the flowing air, allowing a valuable airflow. The combination of UVC and ozone in a single device enables to safely and effectively treat the air and surfaces of an environment and optimize the treatment times. © 2021 IEEE

Deep Convolutional Approaches for the Analysis of COVID-19 Using Chest X-Ray Images From Portable Devices.

The recent human coronavirus disease (COVID-19) is a respiratory infection caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Given the effects of COVID-19 in pulmonary tissues, chest radiography imaging plays an important role in the screening, early detection, and monitoring of the suspected individuals. Hence, as the pandemic of COVID-19 progresses, there will be a greater reliance on the use of portable equipment for the acquisition of chest X-ray images due to its accessibility, widespread availability, and benefits regarding to infection control issues, minimizing the risk of cross-contamination. This work presents novel fully automatic approaches specifically tailored for the classification of chest X-ray images acquired by portable equipment into 3 different clinical categories: normal, pathological, and COVID-19. For this purpose, 3 complementary deep learning approaches based on a densely convolutional network architecture are herein presented. The joint response of all the approaches allows to enhance the differentiation between patients infected with COVID-19, patients with other diseases that manifest characteristics similar to COVID-19 and normal cases. The proposed approaches were validated over a dataset specifically retrieved for this research. Despite the poor quality of the chest X-ray images that is inherent to the nature of the portable equipment, the proposed approaches provided global accuracy values of 79.62%, 90.27% and 79.86%, respectively, allowing a reliable analysis of portable radiographs to facilitate the clinical decision-making process.

Piecewise Isothermal Nucleic Acid Testing (PINAT) for Infectious Disease Detection with Sample-to-Result Integration at the Point-of-Care.

We developed a piecewise isothermal nucleic acid test (PINAT) as a platform technology for diagnosing pathogen-associated infections, empowered by an illustrative novel methodology that embeds an exclusive DNA-mediated specific probing reaction with the backbone of an isothermal reverse transcription cum amplification protocol for detecting viral RNA. In a point-of-care format, this test is executable in a unified single-step, single-chamber procedure, leading to seamless sample-to-result integration in an inexpensive, scalable, pre-programmable, and customizable portable device, with mobile-app-integrated interpretation and analytics involving minimal manually operative procedures. The test exhibited a high sensitivity and specificity of detection when assessed using 200 double-blind patient samples for detecting SARS-CoV-2 infection by the Indian Council of Medical Research (ICMR), and subsequently using 170 double-blind patient samples in a point-of-care format outside controlled laboratory settings as performed by unskilled technicians in an organized clinical trial. We also established its efficacy in detecting Influenza A infection by performing the diagnosis at the point of collection with uncompromised detection rigor. The envisaged trade-off between advanced laboratory-based molecular diagnostic procedures and the elegance of common rapid tests renders the method ideal for deployment in resource-limited settings towards catering the needs of the underserved.

A Portable Device for LAMP Based Detection of SARS-CoV-2.

This paper reports the design, development, and testing of a novel, yet simple and low-cost portable device for the rapid detection of SARS-CoV-2. The device performs loop mediated isothermal amplification (LAMP) and provides visually distinguishable images of the fluorescence emitted from the samples. The device utilises an aluminium block embedded with a cartridge heater for isothermal heating of the sample and a single-board computer and camera for fluorescence detection. The device demonstrates promising results within 20 min using clinically relevant starting concentrations of the synthetic template. Time-to-signal data for this device are considerably lower compared to standard quantitative Polymerase Chain Reaction(qPCR) machine (~10-20 min vs. >38 min) for 1 × 102 starting template copy number. The device in its fully optimized and characterized state can potentially be used as simple to operate, rapid, sensitive, and inexpensive platform for population screening as well as point-of-need severe acute respiratory syndrome-coronavirus 2 (SARS-CoV-2) detection and patient management.

Data augmentation approaches using cycle-consistent adversarial networks for improving COVID-19 screening in portable chest X-ray images.

The current COVID-19 pandemic, that has caused more than 100 million cases as well as more than two million deaths worldwide, demands the development of fast and accurate diagnostic methods despite the lack of available samples. This disease mainly affects the respiratory system of the patients and can lead to pneumonia and to severe cases of acute respiratory syndrome that result in the formation of several pathological structures in the lungs. These pathological structures can be explored taking advantage of chest X-ray imaging. As a recommendation for the health services, portable chest X-ray devices should be used instead of conventional fixed machinery, in order to prevent the spread of the pathogen. However, portable devices present several problems (specially those related with capture quality). Moreover, the subjectivity and the fatigue of the clinicians lead to a very difficult diagnostic process. To overcome that, computer-aided methodologies can be very useful even taking into account the lack of available samples that the COVID-19 affectation shows. In this work, we propose an improvement in the performance of COVID-19 screening, taking advantage of several cycle generative adversarial networks to generate useful and relevant synthetic images to solve the lack of COVID-19 samples, in the context of poor quality and low detail datasets obtained from portable devices. For validating this proposal for improved COVID-19 screening, several experiments were conducted. The results demonstrate that this data augmentation strategy improves the performance of a previous COVID-19 screening proposal, achieving an accuracy of 98.61% when distinguishing among NON-COVID-19 (i.e. normal control samples and samples with pathologies others than COVID-19) and genuine COVID-19 samples. It is remarkable that this methodology can be extrapolated to other pulmonary pathologies and even other medical imaging domains to overcome the data scarcity.

QT interval measurement with portable device during COVID-19 outbreak.

Coronavirus Disease 2019 continues to spread and to date, no definitive treatment is available. Overcrowded and under-resourced healthcare centres have had to design different strategies to treat these patients, what includes the control of the electrocardiogram (ECG), as some drugs that have been used to treat this disease may prolong the QT interval as a side effect. During the COVID-19 outbreak, we designed a protocol for monitoring the QT interval using a portable device with Bluetooth connectivity. After a validation study with 50 patients, we found a very good correlation between the QT interval measured both with this device and with the conventional body surface ECG. In this article, we provide a brief overview of the protocol and then analyse the QT changes observed in a group of patients during their hospitalization and treatment for SARS-CoV-2 infection. 81 patients with confirmed SARS-CoV-2 infection were enrolled in the protocol (age 63.4 SD 17.2 years; 70.3% men), while being treated with lopinavir/ritonavir, azithromycin and hydroxychloroquine, both individually or combined. Ten patients developed long drug-related QT interval, and the QT prolongation was statically significant for all treatment schemes. All patients with drug induced QT prolongation corrected the QT interval following the indications of the protocol, and no patients died of arrhythmic causes after its implementation. In our experience, a protocol for the electrocardiographic monitoring of these patients minimizes the risk of iatrogenic QT interval prolongation and consequently reduces sudden death events, and for that purpose, portable devices like the one used in this protocol may constitute a useful tool to minimize the contact with such patients.